ffmpeg/libswscale/rgb2rgb.c

318 lines
11 KiB
C
Raw Normal View History

/*
* software RGB to RGB converter
* pluralize by software PAL8 to RGB converter
* software YUV to YUV converter
* software YUV to RGB converter
* Written by Nick Kurshev.
* palette & YUV & runtime CPU stuff by Michael (michaelni@gmx.at)
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <inttypes.h>
#include "config.h"
#include "libavutil/bswap.h"
#include "rgb2rgb.h"
#include "swscale.h"
#include "swscale_internal.h"
void (*rgb24tobgr32)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb24tobgr16)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb24tobgr15)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb32tobgr24)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb32to16)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb32to15)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb15to16)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb15tobgr24)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb15to32)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb16to15)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb16tobgr24)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb16to32)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb24tobgr24)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb24to16)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb24to15)(const uint8_t *src, uint8_t *dst, int src_size);
void (*shuffle_bytes_2103)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb32tobgr16)(const uint8_t *src, uint8_t *dst, int src_size);
void (*rgb32tobgr15)(const uint8_t *src, uint8_t *dst, int src_size);
void (*yv12toyuy2)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
int width, int height,
int lumStride, int chromStride, int dstStride);
void (*yv12touyvy)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
int width, int height,
int lumStride, int chromStride, int dstStride);
void (*yuv422ptoyuy2)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
int width, int height,
int lumStride, int chromStride, int dstStride);
void (*yuv422ptouyvy)(const uint8_t *ysrc, const uint8_t *usrc, const uint8_t *vsrc, uint8_t *dst,
int width, int height,
int lumStride, int chromStride, int dstStride);
void (*yuy2toyv12)(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
int width, int height,
int lumStride, int chromStride, int srcStride);
void (*rgb24toyv12)(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
int width, int height,
int lumStride, int chromStride, int srcStride);
void (*planar2x)(const uint8_t *src, uint8_t *dst, int width, int height,
int srcStride, int dstStride);
void (*interleaveBytes)(const uint8_t *src1, const uint8_t *src2, uint8_t *dst,
int width, int height, int src1Stride,
int src2Stride, int dstStride);
void (*vu9_to_vu12)(const uint8_t *src1, const uint8_t *src2,
uint8_t *dst1, uint8_t *dst2,
int width, int height,
int srcStride1, int srcStride2,
int dstStride1, int dstStride2);
void (*yvu9_to_yuy2)(const uint8_t *src1, const uint8_t *src2, const uint8_t *src3,
uint8_t *dst,
int width, int height,
int srcStride1, int srcStride2,
int srcStride3, int dstStride);
void (*uyvytoyuv420)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
int width, int height,
int lumStride, int chromStride, int srcStride);
void (*uyvytoyuv422)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
int width, int height,
int lumStride, int chromStride, int srcStride);
void (*yuyvtoyuv420)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
int width, int height,
int lumStride, int chromStride, int srcStride);
void (*yuyvtoyuv422)(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src,
int width, int height,
int lumStride, int chromStride, int srcStride);
#define RGB2YUV_SHIFT 8
#define BY ((int)( 0.098*(1<<RGB2YUV_SHIFT)+0.5))
#define BV ((int)(-0.071*(1<<RGB2YUV_SHIFT)+0.5))
#define BU ((int)( 0.439*(1<<RGB2YUV_SHIFT)+0.5))
#define GY ((int)( 0.504*(1<<RGB2YUV_SHIFT)+0.5))
#define GV ((int)(-0.368*(1<<RGB2YUV_SHIFT)+0.5))
#define GU ((int)(-0.291*(1<<RGB2YUV_SHIFT)+0.5))
#define RY ((int)( 0.257*(1<<RGB2YUV_SHIFT)+0.5))
#define RV ((int)( 0.439*(1<<RGB2YUV_SHIFT)+0.5))
#define RU ((int)(-0.148*(1<<RGB2YUV_SHIFT)+0.5))
//plain C versions
#include "rgb2rgb_template.c"
/*
RGB15->RGB16 original by Strepto/Astral
ported to gcc & bugfixed : A'rpi
MMX2, 3DNOW optimization by Nick Kurshev
32-bit C version, and and&add trick by Michael Niedermayer
*/
void sws_rgb2rgb_init(void)
{
Merge swscale bloatup This will be cleaned up in the next merge Authorship / merged commits: commit f668afd4896ee65683619b6f165dda4cdd46766f Author: Janne Grunau <janne-libav@jannau.net> Date: Fri Apr 15 09:12:34 2011 +0200 swscale: fix "ISO C90 forbids mixed declarations and code" warning only hit with --enable-runtime-cpudetect commit 7f2ae5c7af374dfe254195a9375974a2ff9395a7 Author: Janne Grunau <janne-libav@jannau.net> Date: Fri Apr 15 02:09:44 2011 +0200 swscale: fix compilation with --enable-runtime-cpudetect commit b6cad3df822969b31bb93eaf677e52a72416bc97 Author: Janne Grunau <janne-libav@jannau.net> Date: Fri Apr 15 00:31:04 2011 +0200 swscale: correct include path to fix ppc altivec build commit 6216fc70b74e01a5272085329aa92f5ac797f9cf Author: Luca Barbato <lu_zero@gentoo.org> Date: Thu Apr 14 22:03:45 2011 +0200 swscale: simplify rgb2rgb templating MMX is always built. Drop the ifdefs commit 33a0421bbaa64f4e9c3d852b7f225ede8dad1388 Author: Josh Allmann <joshua.allmann@gmail.com> Date: Wed Apr 13 20:57:32 2011 +0200 swscale: simplify initialization code Simplify the fallthrough case when no accelerated functions can be initialized. commit 735bf1951171a1e0ee4292e84a1b1beac45dd0ab Author: Josh Allmann <joshua.allmann@gmail.com> Date: Wed Apr 13 20:57:31 2011 +0200 swscale: further cleanup swscale.c Move x86-specific constants out of swscale.c commit 86330b4c9258d5e583c0db033d1e68f46443307c Author: Luca Barbato <lu_zero@gentoo.org> Date: Wed Apr 13 20:57:30 2011 +0200 swscale: partially move the arch specific code left PPC and x86 code is split off from swscale_template.c. Lots of code is still duplicated and should be removed later. Again uniformize the init system to be more similar to the dsputil one. Unset h*scale_fast in the x86 init in order to make the output consistent with the previous status. Thanks to Josh for spotting it. commit c0038328830d7b341c28d7c99b0236a33617fd21 Author: Luca Barbato <lu_zero@gentoo.org> Date: Wed Apr 13 20:57:29 2011 +0200 swscale: move away x86 specific code from rgb2rgb Keep only the plain C code in the main rgb2rgb.c and move the x86 specific optimizations to x86/rgb2rgb.c Change the initialization pattern a little so some of it can be factorized to behave more like dsputils. Conflicts: libswscale/rgb2rgb.c libswscale/swscale_template.c
2011-05-25 03:23:39 +00:00
rgb2rgb_init_c();
if (HAVE_MMX)
rgb2rgb_init_x86();
}
void rgb32to24(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size >> 2;
for (i=0; i<num_pixels; i++) {
#if HAVE_BIGENDIAN
/* RGB32 (= A,B,G,R) -> BGR24 (= B,G,R) */
dst[3*i + 0] = src[4*i + 1];
dst[3*i + 1] = src[4*i + 2];
dst[3*i + 2] = src[4*i + 3];
#else
dst[3*i + 0] = src[4*i + 2];
dst[3*i + 1] = src[4*i + 1];
dst[3*i + 2] = src[4*i + 0];
#endif
}
}
void rgb24to32(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
for (i=0; 3*i<src_size; i++) {
#if HAVE_BIGENDIAN
/* RGB24 (= R,G,B) -> BGR32 (= A,R,G,B) */
dst[4*i + 0] = 255;
dst[4*i + 1] = src[3*i + 0];
dst[4*i + 2] = src[3*i + 1];
dst[4*i + 3] = src[3*i + 2];
#else
dst[4*i + 0] = src[3*i + 2];
dst[4*i + 1] = src[3*i + 1];
dst[4*i + 2] = src[3*i + 0];
dst[4*i + 3] = 255;
#endif
}
}
void rgb16tobgr32(const uint8_t *src, uint8_t *dst, int src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
#if HAVE_BIGENDIAN
*d++ = 255;
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
*d++ = ((bgr&0x7E0)>>3) | ((bgr&0x7E0)>>9);
*d++ = ((bgr&0xF800)>>8) | ((bgr&0xF800)>>13);
#else
*d++ = ((bgr&0xF800)>>8) | ((bgr&0xF800)>>13);
*d++ = ((bgr&0x7E0)>>3) | ((bgr&0x7E0)>>9);
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
*d++ = 255;
#endif
}
}
void rgb16to24(const uint8_t *src, uint8_t *dst, int src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
*d++ = ((bgr&0xF800)>>8) | ((bgr&0xF800)>>13);
*d++ = ((bgr&0x7E0)>>3) | ((bgr&0x7E0)>>9);
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
}
}
void rgb16tobgr16(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = (rgb>>11) | (rgb&0x7E0) | (rgb<<11);
}
}
void rgb16tobgr15(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = (rgb>>11) | ((rgb&0x7C0)>>1) | ((rgb&0x1F)<<10);
}
}
void rgb15tobgr32(const uint8_t *src, uint8_t *dst, int src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
#if HAVE_BIGENDIAN
*d++ = 255;
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
*d++ = ((bgr&0x3E0)>>2) | ((bgr&0x3E0)>>7);
*d++ = ((bgr&0x7C00)>>7) | ((bgr&0x7C00)>>12);
#else
*d++ = ((bgr&0x7C00)>>7) | ((bgr&0x7C00)>>12);
*d++ = ((bgr&0x3E0)>>2) | ((bgr&0x3E0)>>7);
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
*d++ = 255;
#endif
}
}
void rgb15to24(const uint8_t *src, uint8_t *dst, int src_size)
{
const uint16_t *end;
uint8_t *d = dst;
const uint16_t *s = (const uint16_t *)src;
end = s + src_size/2;
while (s < end) {
register uint16_t bgr;
bgr = *s++;
*d++ = ((bgr&0x7C00)>>7) | ((bgr&0x7C00)>>12);
*d++ = ((bgr&0x3E0)>>2) | ((bgr&0x3E0)>>7);
*d++ = ((bgr&0x1F)<<3) | ((bgr&0x1F)>>2);
}
}
void rgb15tobgr16(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned rgb = ((const uint16_t*)src)[i];
((uint16_t*)dst)[i] = ((rgb&0x7C00)>>10) | ((rgb&0x3E0)<<1) | (rgb<<11);
}
}
void rgb15tobgr15(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size >> 1;
for (i=0; i<num_pixels; i++) {
unsigned br;
unsigned rgb = ((const uint16_t*)src)[i];
br = rgb&0x7c1F;
((uint16_t*)dst)[i] = (br>>10) | (rgb&0x3E0) | (br<<10);
}
}
void bgr8torgb8(const uint8_t *src, uint8_t *dst, int src_size)
{
int i;
int num_pixels = src_size;
for (i=0; i<num_pixels; i++) {
unsigned b,g,r;
register uint8_t rgb;
rgb = src[i];
r = (rgb&0x07);
g = (rgb&0x38)>>3;
b = (rgb&0xC0)>>6;
dst[i] = ((b<<1)&0x07) | ((g&0x07)<<3) | ((r&0x03)<<6);
}
}
#define DEFINE_SHUFFLE_BYTES(a, b, c, d) \
void shuffle_bytes_##a##b##c##d(const uint8_t *src, uint8_t *dst, int src_size) \
{ \
int i; \
\
for (i = 0; i < src_size; i+=4) { \
dst[i + 0] = src[i + a]; \
dst[i + 1] = src[i + b]; \
dst[i + 2] = src[i + c]; \
dst[i + 3] = src[i + d]; \
} \
}
DEFINE_SHUFFLE_BYTES(0, 3, 2, 1);
DEFINE_SHUFFLE_BYTES(1, 2, 3, 0);
DEFINE_SHUFFLE_BYTES(3, 0, 1, 2);
DEFINE_SHUFFLE_BYTES(3, 2, 1, 0);